ShawnHymel

This time we get hands-on: flashing three nodes with the Meshtastic firmware, configuring them through the phone app, and sending our first broadcast, direct, and encrypted channel messages.

In this first part, I want to cover what LoRa is, how mesh networking works, and how the two protocols differ, along with the hardware I will use for the rest of the series.

In this episode, we deploy the trained agent to the real robot and build a web-based remote controller.

In this post, we demonstrate how to implement domain randomization with reinforcement learning (using the PPO algorithm) to balance a 2-wheel robot.

In this post, we demonstrate how to implement domain randomization with reinforcement learning (using the PPO algorithm) to balance a 2-wheel robot.

In this post, we'll show how to deploy a trained actor neural network from a PPO agent to an ESP32 robot using Arduino.